Summaries and key ideas, written by Stratmill's research agent, of the books, papers, articles and code our AI agents read. Each page links to its original.
243 documents
This notebook evaluates position-level stop-losses, trailing stops, and time exits on top allocation-stage configurations in a NASDAQ-100 intraday strategy. Decisions occur every fifteen minutes while the backtest engine monitors positions every minute, so…
This chapter frames reinforcement learning as a tool for sequential control, distinguishing it from supervised forecasting. It focuses on tasks where actions affect later outcomes and rewards are comparatively concrete: trade execution, market making, and…
This module defines a point-in-time simulation environment for executing a large sell order in crypto perpetual futures. Its observations combine remaining inventory and time with market volatility, premium index, relative volume, hour of day, and time to…
This chapter presents market data as the result of trading rules, liquidity, and participant behavior. It surveys data from top-of-book quotes through order-level feeds, then describes parsing exchange messages and replaying them into a venue-local limit…
This analysis checks whether daily option data can support a weekly strategy that sells at-the-money straddles on S&P 500 constituents, delta hedges shares, and holds contracts to expiration. It explains how calls and puts form a straddle, how implied and…
This case study lays out a research pipeline for crypto perpetual futures, treating funding payments exchanged between long and short positions at regular settlements as a potential return source. It describes data and model stages from label construction…
The document explains how four market-impact models estimate the adverse per-share price move associated with an order: no impact, linear impact, square-root impact, and a configurable power law. It clarifies the sign convention, the roles of participation,…
This notebook examines why two backtesting engines can produce different results from identical signals. It holds the strategy and tradable universe fixed, makes portfolio weights deterministic when predictions tie, and exposes execution settings such as…
This chapter treats a backtest as an attempt to falsify a strategy through explicit assumptions about signal timing, execution, rebalancing, sizing, costs, constraints, and benchmarks. It compares vectorized and event-driven simulation by their treatment of…
This capstone notebook compares equal weight, inverse volatility, mean-variance optimization, and hierarchical risk parity using a common signal on a diversified ETF universe. A rolling Ridge model uses momentum, moving-average distance, and volatility…
This notebook describes reconstructing a NASDAQ limit order book from DataBento market-by-order messages for a single symbol and trading day. It lays out a modular engine that tracks individual order state, aggregates orders into price levels, and maintains…
This notebook examines how rebalancing cadence affects turnover, gross performance, and cost-adjusted results for a top-ranked momentum portfolio of ETFs. It estimates turnover from historical target-weight changes at daily, weekly, biweekly, and monthly…
This notebook describes a 15-minute backtest workflow for predictions on NASDAQ-100 stocks. It first runs a random-signal plumbing check: because random trading should lose after costs, a persistently profitable result can indicate problems such as…
This notebook constructs market microstructure measures from NASDAQ ITCH trade data, aggregates trades into intraday bars, and distinguishes liquidity proxies from order-flow signals and order-book state. It classifies individual trades with a tick rule…
This demo outlines an always-on crypto trading loop connected to Alpaca’s USD spot market. It maps a perpetual-futures case-study universe to the venue’s supported spot pairs, making clear that only a subset can be traded there. The example signal is a…
This notebook compares portfolio allocations from PyPortfolioOpt, Riskfolio-Lib, and skfolio using the same ETF return panel. It fits allocators on a training period, checks that equivalent objectives and aligned weights agree within solver tolerances, and…
This notebook studies how transaction costs affect a frequently rebalanced NASDAQ-100 strategy. It first applies basis-point cost assumptions to existing pre-cost backtests to show how Sharpe changes as costs rise. It then compares full-universe and…
This notebook turns model rankings into simple crypto perpetual-futures portfolios so later experiments can measure the effect of changing sizing, costs, or risk controls. It applies entry rules such as selecting the highest-scored contracts for longs and…
This document demonstrates connecting a five-day ETF momentum strategy to Alpaca through a shared strategy interface. The strategy tracks momentum across SPY, QQQ, and IWM and generates signals when it crosses a threshold. Broker-specific adapters handle…
This notebook turns model prediction sets into comparable S&P 500 options backtests. On each weekly decision date, it ranks predicted returns, selects the highest-ranked symbols in the liquid universe, and sells equally weighted at-the-money straddles.…
This notebook demonstrates how to configure Feast with Parquet sources, entities, feature views, timestamps, and a time-to-live policy, then retrieve features for training examples and a live-style as-of query. It compares Feast’s output feature by feature…
This exploratory notebook describes the structure and interpretation of AlgoSeek NASDAQ-100 minute bars. It organizes the dataset’s precomputed fields into quote prices and sizes, trade prices, spreads, volume, trade-location buckets, tick direction,…
This configuration note distinguishes settings that appear in a backtest identity from settings that actually affect simulated trading costs. In the described case study, all registered runs use a vectorized, return-to-expiry path. The configured…
The document demonstrates a broker wrapper that checks orders and portfolio state before forwarding trades. Its controls include per-order share and value caps, position exposure limits, order-rate limits, asset allow and block lists, and an emergency halt.…